Learning-Based Context-Aware Resource Allocation for Edge-Computing-Empowered Industrial IoT

Haijun Liao, Zhenyu Zhou, Xiongwen Zhao, Lei Zhang, Shahid Mumtaz, Alireza Jolfaei, Syed Hassan Ahmed, Ali Kashif Bashir

Research output: Contribution to journalArticlepeer-review

202 Citations (Scopus)


Edge computing provides a promising paradigm to support the implementation of Industrial Internet of Things (IIoT) by offloading computational-intensive tasks from resource-limited machine-type devices (MTDs) to powerful edge servers. However, the performance gain of edge computing may be severely compromised due to limited spectrum resources, capacity-constrained batteries, and context unawareness. In this article, we consider the optimization of channel selection that is critical for efficient and reliable task delivery. We aim at maximizing the long-term throughput subject to long-term constraints of energy budget and service reliability. We propose a learning-based channel selection framework with service reliability awareness, energy awareness, backlog awareness, and conflict awareness, by leveraging the combined power of machine learning, Lyapunov optimization, and matching theory. We provide rigorous theoretical analysis, and prove that the proposed framework can achieve guaranteed performance with a bounded deviation from the optimal performance with global state information (GSI) based on only local and causal information. Finally, simulations are conducted under both single-MTD and multi-MTD scenarios to verify the effectiveness and reliability of the proposed framework.

Original languageEnglish
Pages (from-to)4260-4277
Number of pages18
JournalIEEE Internet of Things Journal
Issue number5
Publication statusPublished - May 2020
Externally publishedYes


  • Context awareness
  • edge computing
  • Industrial Internet of Things (IIoT)
  • Lyapunov optimization
  • machine learning
  • matching theory
  • resource allocation


Dive into the research topics of 'Learning-Based Context-Aware Resource Allocation for Edge-Computing-Empowered Industrial IoT'. Together they form a unique fingerprint.

Cite this